© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128921
    Prev
    Next
    INDEX
    Explanations

    describing structural components and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     KeyError
    0.48
     pug
    0.43
     Encryption
    0.43
    レッ
    0.43
    マ
    0.42
    zeichnung
    0.42
     immunoprec
    0.41
    auer
    0.41
     パン
    0.41
     экстра
    0.41
    POSITIVE LOGITS
    рованные
    0.50
    ными
    0.48
    所需的
    0.46
    斯坦
    0.46
    ष्‍ट्र
    0.46
    >(</
    0.45
    vehicles
    0.45
    াহিয়া
    0.44
    atorics
    0.43
    рованной
    0.43
    Activations Density 0.001%

    No Known Activations